Koukyosyumei/AIJack
Security and Privacy Risk Simulator for Machine Learning (arXiv:2312.17667)
Implements 30+ attack and defense methods (poisoning, model inversion, backdoor, membership inference) with PyTorch and scikit-learn integration, using a C++ backend for performance. Provides modular APIs for both centralized models and distributed learning schemes (federated, split learning) via `Client`/`Server`/`Manager` abstractions with MPI support. Includes AIValut, a SQL-based debugging system for ML models with built-in constraint validation and automated record removal for model correction.
422 stars.
Stars
422
Forks
67
Language
C++
License
Apache-2.0
Category
Last pushed
Jan 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Koukyosyumei/AIJack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
google/scaaml
SCAAML: Side Channel Attacks Assisted with Machine Learning
pralab/secml
A Python library for Secure and Explainable Machine Learning
AI-SDC/SACRO-ML
Collection of tools and resources for managing the statistical disclosure control of trained...
liuyugeng/ML-Doctor
Code for ML Doctor
ArtLabss/open-data-anonymizer
Python Data Anonymization & Masking Library For Data Science Tasks